方法对比

	知识蒸馏	神经架构搜索	随机森林	支持向量机（分类）
领域	深度学习	深度学习	机器学习	机器学习
方法族	Machine learning	Machine learning	Machine learning	Machine learning
起源年份	2015	2017	2001	1995
提出者	Hinton, G., Vinyals, O. & Dean, J.	Zoph, B. & Le, Q.V.	Breiman, L.	Cortes, C. & Vapnik, V.
类型	Neural network compression (teacher–student)	Automated architecture optimization (deep learning)	Ensemble (bagging of decision trees)	Maximum-margin classifier (kernel method)
开创性文献	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
别名	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
相关	5	5	4	5
摘要	Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.	Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All.	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.	The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.